Accurate detection of surgical actions in minimally invasive procedures is a critical step toward developing intelligent operative assistance systems. In this work, we propose Surgical You Only Look Once detector (Surg-YOLO), an efficient and high-precision surgical action detection framework built upon the YOLO version 11 (YOLOv11) architecture, specifically optimized for the spatio-temporal complexities of surgical environments. Surg-YOLO integrates three key architectural innovations: the Enhanced Spatial Pyramid Pooling-Fast (ESPPF) module for capturing rich multi-scale spatial features; the Spatio-Temporal Multi-scale Context Aggregation Module (ST-MCAM), which enhances temporal reasoning and contextual awareness across frames; and the Decoupled Dual-Branch Prediction Head (DDPH) for independently refining classification and localization tasks. Extensive experiments on a large-scale surgical action dataset demonstrate that Surg-YOLO significantly outperforms existing baseline models, achieving superior detection accuracy across multiple evaluation thresholds. Qualitative visualizations further validate the model’s ability to localize subtle and concurrent surgical actions with high precision. These results highlight Surg-YOLO’s potential as a reliable solution for real-time surgical action detection.

Illumination planning in photometric stereo aims to find a balance between surface normal estimation accuracy and image capturing efficiency by selecting optimal light configurations. It depends on factors such as the unknown shape and general reflectance of the target object, global illumination, and the choice of photometric stereo backbones, which are too complex to be handled by existing methods based on handcrafted illumination planning rules. This paper proposes a learning-based illumination planning method that jointly considers these factors via integrating a neural network and a generalized image formation model. As it is impractical to supervise illumination planning due to the enormous search space for ground truth light configurations, we formulate illumination planning using reinforcement learning, which explores the light space in a photometric stereo-aware and reward-driven manner. Experiments on synthetic and real-world datasets demonstrate that photometric stereo under the 20-light configurations from our method is comparable to, or even surpasses that of using lights from all available directions.